Long-term Task-oriented Agent: Proactive Long-term Intent Maintenance in Dynamic Environments

2026-01-14

AI Summary

This work proposes a novel proactive, task-oriented agent paradigm to address the limitations of existing large language model agents, which predominantly operate in a passive response mode and struggle to maintain user intent or adapt proactively in dynamic environments. The proposed framework bridges static user goals and evolving contexts through two key mechanisms: intent-conditioned monitoring and event-triggered follow-up. To support this approach, we develop a high-quality synthetic data pipeline that encompasses trigger condition generation, environmental event detection, and multi-turn complex dialogue synthesis. We also introduce ChronosBench, the first benchmark specifically designed for evaluating dynamic task-oriented interactions. Experimental results show that our fine-tuned model achieves an 85.19% task completion rate on complex tasks involving intent shifts, significantly outperforming both leading open-source and closed-source models.

Technology Category

• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Multiagent Systems: Modeling other Agents
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Search and Retrieval-Augmented AI: Agentic search

Abstract

Current large language model agents predominantly operate under a reactive paradigm, responding only to immediate user queries within short-term sessions. This limitation hinders their ability to maintain long-term user's intents and dynamically adapt to evolving external environments. In this paper, we propose a novel interaction paradigm for proactive Task-oriented Agents capable of bridging the gap between relatively static user's needs and a dynamic environment. We formalize proactivity through two key capabilities, (i) Intent-Conditioned Monitoring: The agent autonomously formulates trigger conditions based on dialog history; (ii) Event-Triggered Follow-up: The agent actively engages the user upon detecting useful environmental updates. We introduce a high-quality data synthesis pipeline to construct complex, multi-turn dialog data in a dynamic environment. Furthermore, we attempt to address the lack of evaluation criteria of task-oriented interaction in a dynamic environment by proposing a new benchmark, namely ChronosBench. We evaluated some leading close-source and open-source models at present and revealed their flaws in long-term task-oriented interaction. Furthermore, our fine-tuned model trained using synthetic data for supervised learning achieves a task completion rate of 85.19% for complex tasks including shifts in user intent, outperforming other models under test. And the result validated the effectiveness of our data-driven strategy.

Problem

• long-term intent
• proactive agent
• dynamic environment
• task-oriented interaction
• intent maintenance

Innovation

• Proactive Agent
• Intent-Conditioned Monitoring
• Event-Triggered Follow-up
• Dynamic Environment
• ChronosBench